@inproceedings{kim-etal-2025-semantic,
    title = "Semantic Inversion, Identical Replies: Revisiting Negation Blindness in Large Language Models",
    author = "Kim, Jinsung  and
      Koo, Seonmin  and
      Lim, Heuiseok",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1088/",
    pages = "21445--21482",
    ISBN = "979-8-89176-332-6",
    abstract = "Large language models (LLMs) often fail to capture semantic changes in queries due to negation, and generate incorrect responses. Negation frequently exists in the real world and is useful for understanding the opposite or absence of a statement, so it is an essential element in logical reasoning. Previous studies have explored LLMs' ability to capture negations `separately' from their ability to properly ground knowledge for positive queries. However, this perspective is limited in that it cannot clearly distinguish whether the cause of incorrect responses is the logical incoherence caused by negations or the lack of grounding ability for the given context. To address this issue, we focus on the phenomenon of the model failing to capture semantic contradictions in negated queries despite its accurate understanding of knowledge about positive queries. We term this phenomenon \textit{negation blindness} on the query. We propose a verification framework that includes task design and measurement methods to verify this issue. In detail, we establish two criteria for systematic task design{--}i) `complexity' and ii) `constrainedness'{--}and devise four verification tasks accordingly. Moreover, we analyze the results extensively and provide insights into problem alleviation feasibility through experiments on various approaches. Our code and resources can be found at https://www.github.com/jin62304/NegationBlindness."
}